© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25081
    Prev
    Next
    INDEX
    Explanations

    terms associated with adrenaline and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    343
    +0.14
    0.8%
    321
    +0.13
    0.7%
    443
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.01
    443
    +0.13
    0.01
    468
    +0.13
    0.01
    Negative Logits
     else
    -2.06
    abouts
    -1.62
     Lastly
    -1.55
     Soon
    -1.55
     Illumina
    -1.54
    uppose
    -1.53
     Offic
    -1.49
    DOCTYPE
    -1.49
     Parenthood
    -1.49
     HOWEVER
    -1.46
    POSITIVE LOGITS
    ¥
    4.25
    Ī
    4.07
    ¢
    4.07
    ħ
    4.01
    Ŀ
    3.93
    §
    3.93
    Ģ
    3.91
    ±
    3.81
    ĸ
    3.80
    ®
    3.76
    Activations Density 0.044%

    No Known Activations